首个开源网络安全推理模型，80亿参数实现强安全分析能力。
Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report
- 基于Llama-3.1-8B微调，结合监督与可验证奖励强化学习。
- 在10个安全基准上性能媲美更大模型，通用能力亦强。
- 适合安全研究、红队测试与自动化威胁分析场景使用。
我们提出Foundation-Sec-8B-Reasoning，首个开源的网络安全原生推理模型。基于此前发布的Foundation-Sec-8B基础模型（源自Llama-3.1-8B-Base），采用两阶段训练：监督微调（SFT）与可验证奖励强化学习（RLVR）。训练数据涵盖网络安全分析、指令遵循和数学推理等专有内容。在10个网络安全基准和10个通用基准上的评估显示，该模型在安全任务上表现媲美更大模型，同时保持强大的通用能力。模型在多跳推理任务中表现出良好泛化性，在适当系统提示与防护机制下具备优异安全性。本工作证明，领域专用推理模型可在保持广泛通用能力的同时，实现专业化任务的高性能。模型已公开发布于https://huggingface.co/fdtn-ai/Foundation-Sec-8B-Reasoning。
原文摘要 · Abstract (English)
We present Foundation-Sec-8B-Reasoning, the first open-source native reasoning model for cybersecurity. Built upon our previously released Foundation-Sec-8B base model (derived from Llama-3.1-8B-Base), the model is trained through a two-stage process combining supervised fine-tuning (SFT) and reinforcement learning from verifiable rewards (RLVR). Our training leverages proprietary reasoning data spanning cybersecurity analysis, instruction-following, and mathematical reasoning. Evaluation across 10 cybersecurity benchmarks and 10 general-purpose benchmarks demonstrates performance competitive with significantly larger models on cybersecurity tasks while maintaining strong general capabilities. The model shows effective generalization on multi-hop reasoning tasks and strong safety performance when deployed with appropriate system prompts and guardrails. This work demonstrates that domain-specialized reasoning models can achieve strong performance on specialized tasks while maintaining broad general capabilities. We release the model publicly at https://huggingface.co/fdtn-ai/Foundation-Sec-8B-Reasoning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。